Data Analytics for Noise Reduction in Optical Metrology of Reflective Planar Surfaces

Abstract

On-line data collection from the manufactured parts is an essential element in Industry 4.0 to monitor the production’s health, which required strong data analytics. The optical metrology-based inspection of highly reflective parts in a production line, such as parts with metallic surfaces, is a difficult challenge. As many on-line inspection paradigms require the use of optical sensors, this reflectivity can lead to large amounts of noise, rendering the scan inaccurate. This paper discusses a method for noise reduction and removal in datapoints resulting from scanning the reflective planar surfaces. Utilizing a global statistic-based iterative approach, noise is gradually removed from the dataset at increasing percentages. The change in the standard deviation of point-plane distances is examined, and an optimal amount of noisy data is removed to reduce uncertainty in representing the workpiece. The developed algorithm provides a fast and efficient method for noise reduction in optical coordinate metrology and scanning.